Fast Construction of Correcting Ensembles for Legacy Artificial Intelligence Systems: Algorithms and a Case Study

TL;DR

This paper introduces a fast, theoretically grounded method for enhancing existing AI systems by constructing small ensemble corrections that efficiently eliminate errors, demonstrated through a case study on sign language digit recognition.

Contribution

The paper proposes a novel, computationally efficient ensemble construction technique based on stochastic separation theorems, applicable to existing neural networks for error correction.

Findings

Enables near-instantaneous removal of errors with high probability.

Works effectively on large, high-dimensional datasets.

Validated through numerical experiments and a sign language recognition case study.

Abstract

This paper presents a technology for simple and computationally efficient improvements of a generic Artificial Intelligence (AI) system, including Multilayer and Deep Learning neural networks. The improvements are, in essence, small network ensembles constructed on top of the existing AI architectures. Theoretical foundations of the technology are based on Stochastic Separation Theorems and the ideas of the concentration of measure. We show that, subject to mild technical assumptions on statistical properties of internal signals in the original AI system, the technology enables instantaneous and computationally efficient removal of spurious and systematic errors with probability close to one on the datasets which are exponentially large in dimension. The method is illustrated with numerical examples and a case study of ten digits recognition from American Sign Language.